Analyzing and Classifying Signaling Sets or Calls

1. An apparatus comprising: at least one processing circuitry, and at least one memory for storing instructions to be executed by the processing circuitry, wherein the at least one memory and the instructions are configured to, with the at least one processing circuitry, cause the apparatus at least: to analyze a plurality of separate signaling sets with regard to similarities and dissimilarities between at least two of the plurality of the signaling sets for classifying each signaling set into at least one class of signaling sets in accordance with a result of the analysis, wherein the analyzing comprises transforming trace data representing a respective one of the plurality of signaling sets for generating a signaling set sequence according to a sequence model by filtering predetermined information from the trace data, wherein the signaling set sequence being generated comprises an ordered list of sequence elements representing a relevant part of the trace data, wherein the sequence elements are selected from a plurality of types of sequence elements, each type being differentiated and assigned to a unique identifier, wherein the sequence element comprises at least one of a scalar identifier and an information element derived from the trace data, evaluating a distance of signaling sets by using respective signaling set sequences, wherein the distance is indicated by a distance metric, and assigning the respective signaling set to a signaling set class on the basis of the distance metric.

2. The apparatus according to claim 1 , wherein each signaling set is a result of a signaling between a plurality of network elements or functions or within a network element or function, the signaling comprising a series of messages or context data in at least one of a data communication, a voice communication, a message exchange between software blocks involving one or more network elements or functions and protocol stacks, and the trace data comprise information about at least one of individual events and messages of the signaling set, user plane events, status change events, update events, failure counter events, and properties related to events or messages.

3. The apparatus according to claim 1 , wherein the at least one memory and the instructions are further configured to, with the at least one processing circuitry, cause the apparatus at least: to preselect the plurality of separate signaling sets for analyzing in accordance with a type of failure indication comprised in the signaling sets.

4. The apparatus according to claim 1 , wherein the at least one memory and the instructions are further configured to, with the at least one processing circuitry, cause the apparatus at least: for transforming the trace data representing a respective one of the plurality of signaling sets for generating the signaling set sequence according to a sequence model, to differentiate parts of the trace data for identifying specific elements, to assign to each specific element a corresponding identifier, and to generate the signaling set sequence by using the assigned identifiers.

5. The apparatus according to any of claim 1 , wherein the at least one memory and the instructions are further configured to, with the at least one processing circuitry, cause the apparatus at least: to adapt, for transforming the trace data representing a respective one of the plurality of signaling sets for generating the signaling set sequence according to a sequence model, the filtering of the predetermined information from the trace data to a processing conducted for evaluating the distance of signaling sets, wherein results of the transforming of the respective trace data correspond to a common sequence model being suitable for the processing conducted for evaluating the distance of signaling sets.

6. The apparatus according to any of claim 1 , wherein the at least one memory and the instructions are further configured to, with the at least one processing circuitry, cause the apparatus at least: to compute, for evaluating the distance of the signaling sets, a distance of at least two signaling set sequences derived from the plurality of signaling sets to each other or a distance of signaling set sequences derived from the plurality of signaling sets to at least one pre-stored reference sequence set, wherein the distance metric is determined by aligning the signaling set sequences under consideration of a specific element in each signaling set sequence, wherein the specific element in each signaling set sequence is related to one of a failure event in the trace data, a first element of the signaling set sequence, and a last element of the signaling set sequence.

7. The apparatus according to claim 6 , wherein the at least one memory and the instructions are further configured to, with the at least one processing circuitry, cause the apparatus at least: to determine, as the distance metric, one of a Dynamic Hamming Distance, a Levenshtein distance and a Jaccard distance, and to modulate a result of the distance metric determination with a weighting factor function being dependent on a distance between a position in the signaling set sequence to the specific element used for alignment.

8. The apparatus according to any of claim 1 , wherein the at least one memory and the instructions are further configured to, with the at least one processing circuitry, cause the apparatus at least: to consider the distance metric for assigning signaling sets which fulfill a predetermined similarity condition with each other to the same signaling set class and for assigning signaling sets which do not fulfill the predetermined similarity condition with each other to another signaling set class.

9. The apparatus according to any of claim 1 , wherein the at least one memory and the instructions are further configured to, with the at least one processing circuitry, cause the apparatus at least: to analyze a plurality of separate signaling sets in one of an off-line mode and an on-line mode, wherein in the off-line mode, the plurality of signaling sets is a closed set of previously stored signaling sets, and in the on-line mode, the plurality of signaling sets is input in a subsequent manner and the analyzing is conducted in accordance with an arrival of signaling sets for an arbitrary time period.

10. The apparatus according to claim 9 , wherein the at least one memory and the instructions are further configured to, with the at least one processing circuitry, cause the apparatus at least: in the off-line mode, to use at least one of the signaling set classes as a reference signaling set class defining a signaling set sequence to be used in a distance evaluation in a signaling set analysis in at least one of the off-line mode and the on-line mode.

11. The apparatus according to claim 9 , wherein the at least one memory and the instructions are further configured to, with the at least one processing circuitry, cause the apparatus at least: in the off-line mode, to evaluate the distance of the signaling sets by aligning the signaling set sequences to a specific element of the signaling set sequences corresponding to a failure counter incrementing event in the trace data, to compute pairwise distances of the signaling set sequences as a distance matrix according to the distance metric, and to use, for assigning the signaling sets to a signaling set class, a partitioning or clustering processing for identifying subsets of signaling set sequences with a distance being equal to or lower than a predetermined distance by using the distance matrix.

12. The apparatus according to claim 9 , wherein the at least one memory and the instructions are further configured to, with the at least one processing circuitry, cause the apparatus at least: in the on-line mode, to use at least one reference signaling set class each comprising at least one reference signaling set sequence for evaluating a distance of a signaling sets and for assigning the signaling sets to a signaling set class, and to define, in case a signaling set is not assignable according to any reference signaling set class, a new reference signaling set class on the basis of the not assignable signaling set.

13. The apparatus according to claim 9 , wherein the at least one memory and the instructions are further configured to, with the at least one processing circuitry, cause the apparatus at least: in the on-line mode, to evaluate the distance of the signaling sets by aligning the signaling set sequences to a reference signaling set sequence, to compute pairwise distances of the signaling set sequence and the reference signaling set sequence as a distance vector according to the distance metric, to determine on the basis of the distance vector whether the signaling set is to be assigned to a signaling set class being the closest signaling set class or defines a new signaling set class.

14. The apparatus according to claim 1 , wherein the at least one memory and the instructions are further configured to, with the at least one processing circuitry, cause the apparatus at least: to provide results of the analysis of the signaling sets for a post-processing related to changes in analysis results over the time.

15. The apparatus according to claim 1 , wherein the apparatus is included in a network element or function configured to act as a network control element or function or to act as an analysis element or function, wherein the network is communication network.

16. A method comprising: analyzing a plurality of separate signaling sets with regard to similarities and dissimilarities between at least two of the plurality of the signaling sets for classifying each signaling set into at least one class of signaling sets in accordance with a result of the analysis, wherein the analyzing comprises transforming trace data representing a respective one of the plurality of signaling sets for generating a signaling set sequence according to a sequence model by filtering predetermined information from the trace data, wherein the signaling set sequence being generated comprises an ordered list of sequence elements representing a relevant part of the trace data, wherein the sequence elements are selected from a plurality of types of sequence elements, each type being differentiated and assigned to a unique identifier, wherein the sequence element comprises at least one of a scalar identifier and an information element derived from the trace data, evaluating a distance of signaling sets by using respective signaling set sequences, wherein the distance is indicated by a distance metric, and assigning the respective signaling set to a signaling set class on the basis of the distance metric.

17. The method according to claim 16 , further comprising: computing, for evaluating the distance of the signaling sets, a distance of at least two signaling set sequences derived from the plurality of signaling sets to each other or a distance of signaling set sequences derived from the plurality of signaling sets to at least one pre-stored reference sequence set, wherein the distance metric is determined by aligning the signaling set sequences under consideration of a specific element in each signaling set sequence, wherein the specific element in each signaling set sequence is related to one of a failure event in the trace data, a first element of the signaling set sequence, and a last element of the signaling set sequence.

18. A computer program product, comprising a computer usable medium having a computer readable program code embodied therein, the computer readable program code adapted to execute a process comprising: analyzing a plurality of separate signaling sets with regard to similarities and dissimilarities between at least two of the plurality of the signaling sets for classifying each signaling set into at least one class of signaling sets in accordance with a result of the analysis, wherein the analyzing comprises transforming trace data representing a respective one of the plurality of signaling sets for generating a signaling set sequence according to a sequence model by filtering predetermined information from the trace data, wherein the signaling set sequence being generated comprises an ordered list of sequence elements representing a relevant part of the trace data, wherein the sequence elements are selected from a plurality of types of sequence elements, each type being differentiated and assigned to a unique identifier, wherein the sequence element comprises at least one of a scalar identifier and an information element derived from the trace data, evaluating a distance of signaling sets by using respective signaling set sequences, wherein the distance is indicated by a distance metric, and assigning the respective signaling set to a signaling set class on the basis of the distance metric.